All skills
earth2studio-deterministic-forecast
Generate a runnable Earth2Studio deterministic forecast script with model, data source, IO backend, and nsteps.
- Part of NVIDIA/skills
- 1.9k installs
- Machine Learning · Model research
When to use it
You have a forecast horizon, target variables, and region in mind but still need a working single-member inference script wired to a compatible model and data source.
For example
You say
Use earth2studio-deterministic-forecast to write a script for a 5-day global forecast of t2m and wind from 2024-01-01T00:00:00, saving to Zarr.
You get
- Forecast Python script
- Model and data source choices
- nsteps calculation
How it works
- Checks that the data source provides every model input variable before pairing them.
- Filters output to requested variables only, or keeps all when unspecified.
- Offers a manual loop alternative when the run.deterministic helper isn't wanted.
Before installing
Requires Earth2Studio installed with a CUDA-capable GPU, Python 3.10+, and network access for model weights and data.
This skill includes 4 scripts your assistant may run on your computer.
Also in this pack
- accelerated-computing-cudf3.2kGuides GPU DataFrame work with cuDF, including pandas acceleration, joins, groupby, file I/O and multi-GPU jobs.
- cuopt-developer2.8kModifies, builds, tests, and debugs NVIDIA cuOpt source code and prepares contributions.
- cuopt-install2.6kInstalls cuOpt for Python, C, or server via pip, conda, or Docker and verifies it works.
- data-designer2.6kGenerates a synthetic dataset from your description of the data you need.